Improvement of multi-task learning by data enrichment: application for drug discovery

Multi-task learning in deep neural networks has become a topic of growing importance in many research fields, including drug discovery. However, applying multi-task learning poses new challenges in improving prediction performance. This study investigated the potential of training data enrichment to enhance multi-task model prediction quality in drug discovery. The study evaluated four scenarios with varying degrees of information capacity of the training data and applied two types of test data to evaluate prediction performance. We used three datasets: ViralChEMBL, which consisted of binary activities of compounds against viral species, was applied for the classification task; pQSAR(159) and pQSAR(4267), which consisted of bio-activities of compounds and assays from the research of the profile-QSAR method, were applied for regression tasks. We built multi-task models based on the feed-forward DNNs using the PyTorch framework. Our findings showed that training data enrichment could be an effective means of enhancing prediction performance in multi-task learning, but the degree of improvement depends on the quality of the training data. The more unique compounds and targets the training data included, the more new compound-target interactions are required for prediction improvement. Also, we found out that even using multi-task learning, one could not predict the interactions of compounds that are highly dissimilar from those used for model training. The study provides some recommendations for effectively employing multi-task learning in drug discovery to improve prediction accuracy and facilitate the discovery of novel drug candidates.

GenUI: interactive and extensible open source software platform for de novo molecular generation and cheminformatics

Many contemporary cheminformatics methods, including computer-aided de novo drug design, hold promise to significantly accelerate and reduce the cost of drug discovery. Thanks to this attractive outlook, the field has thrived and in the past few years has seen an especially significant growth, mainly due to the emergence of novel methods based on deep neural networks. This growth is also apparent in the development of novel de novo drug design methods with many new generative algorithms now available. However, widespread adoption of new generative techniques in the fields like medicinal chemistry or chemical biology is still lagging behind the most recent developments. Upon taking a closer look, this fact is not surprising since in order to successfully integrate the most recent de novo drug design methods in existing processes and pipelines, a close collaboration between diverse groups of experimental and theoretical scientists needs to be established. Therefore, to accelerate the adoption of both modern and traditional de novo molecular generators, we developed Generator User Interface (GenUI), a software platform that makes it possible to integrate molecular generators within a feature-rich graphical user interface that is easy to use by experts of diverse backgrounds. GenUI is implemented as a web service and its interfaces offer access to cheminformatics tools for data preprocessing, model building, molecule generation, and interactive chemical space visualization. Moreover, the platform is easy to extend with customizable frontend React.js components and backend Python extensions. GenUI is open source and a recently developed de novo molecular generator, DrugEx, was integrated as a proof of principle. In this work, we present the architecture and implementation details of GenUI and discuss how it can facilitate collaboration in the disparate communities interested in de novo molecular generation and computer-aided drug discovery.

Should We Embed in Chemistry? A Comparison of Unsupervised Transfer Learning with PCA, UMAP, and VAE on Molecular Fingerprints

Methods for dimensionality reduction are showing significant contributions to knowledge generation in high-dimensional modeling scenarios throughout many disciplines. By achieving a lower dimensional representation (also called embedding), fewer computing resources are needed in downstream machine learning tasks, thus leading to a faster training time, lower complexity, and statistical flexibility. In this work, we investigate the utility of three prominent unsupervised embedding techniques (principal component analysis-PCA, uniform manifold approximation and projection-UMAP, and variational autoencoders-VAEs) for solving classification tasks in the domain of toxicology. To this end, we compare these embedding techniques against a set of molecular fingerprint-based models that do not utilize additional pre-preprocessing of features. Inspired by the success of transfer learning in several fields, we further study the performance of embedders when trained on an external dataset of chemical compounds. To gain a better understanding of their characteristics, we evaluate the embedders with different embedding dimensionalities, and with different sizes of the external dataset. Our findings show that the recently popularized UMAP approach can be utilized alongside known techniques such as PCA and VAE as a pre-compression technique in the toxicology domain. Nevertheless, the generative model of VAE shows an advantage in pre-compressing the data with respect to classification accuracy.

From Big Data to Artificial Intelligence: chemoinformatics meets new challenges

The increasing volume of biomedical data in chemistry and life sciences requires development of new methods and approaches for their analysis. Artificial Intelligence and machine learning, especially neural networks, are increasingly used in the chemical industry, in particular with respect to Big Data. This editorial highlights the main results presented during the special session of the International Conference on Neural Networks organized by "Big Data in Chemistry" project and draws perspectives on the future progress of the field.

Data Mining Approach for Extraction of Useful Information About Biologically Active Compounds from Publications

A lot of high quality data on the biological activity of chemical compounds are required throughout the whole drug discovery process: from development of computational models of the structure-activity relationship to experimental testing of lead compounds and their validation in clinics. Currently, a large amount of such data is available from databases, scientific publications, and patents. Biological data are characterized by incompleteness, uncertainty, and low reproducibility. Despite the existence of free and commercially available databases of biological activities of compounds, they usually lack unambiguous information about peculiarities of biological assays. On the other hand, scientific papers are the primary source of new data disclosed to the scientific community for the first time. In this study, we have developed and validated a data-mining approach for extraction of text fragments containing description of bioassays. We have used this approach to evaluate compounds and their biological activity reported in scientific publications. We have found that categorization of papers into relevant and irrelevant may be performed based on the machine-learning analysis of the abstracts. Text fragments extracted from the full texts of publications allow their further partitioning into several classes according to the peculiarities of bioassays. We demonstrate the applicability of our approach to the comparison of the endpoint values of biological activity and cytotoxicity of reference compounds.

A chemoinformatics approach for the characterization of hybrid nanomaterials: safer and efficient design perspective

In this study, photocatalytic properties and in vitro cytotoxicity of 29 TiO2-based multi-component nanomaterials (i.e., hybrids of more than two composition types of nanoparticles) were evaluated using a combination of the experimental testing and supervised machine learning modeling. TiO2-based multi-component nanomaterials with metal clusters of silver, and their mixtures with gold, palladium, and platinum were successfully synthesized. Two activities, photocatalytic activity and cytotoxicity, were studied. A novel cheminformatic approach was developed and applied for the computational representation of the photocatalytic activity and cytotoxicity effect. In this approach, features of investigated TiO2-based hybrid nanomaterials were reflected by a series of novel additive descriptors for hybrid and hybrid nanostructures (denoted as "hybrid nanosctructure descriptors"). These descriptors are based on quantum chemical calculations and the Smoluchowski equation. The obtained experimental data and calculated hybrid-nanostructure descriptors were used to develop novel predictive Quantitative Structure-Activity Relationship computational models (called "nano-QSARmix"). The proposed modeling approach is an initial step in the understanding of the relationships between physicochemical properties of hybrid nanoparticles, their toxicity, and photochemical activity under UV-vis irradiation. Acquired knowledge supports the safe-by-design approaches relevant to the development of efficient hybrid nanomaterials with reduced hazardous effects.

Virtual Chemical Libraries

Advances in computer processing speed and storage capacity have enabled researchers to generate virtual chemical libraries containing billions of molecules. While these numbers appear large, they are only a small fraction of the number of organic molecules that could potentially be synthesized. This review provides an overview of recent advances in the generation and use of virtual chemical libraries in medicinal chemistry. We also consider the practical implications of these libraries in drug discovery programs and highlight a number of current and future challenges.

Computational prediction of chemical reactions: current status and outlook

Over the past few decades, various computational methods have become increasingly important for discovering and developing novel drugs. Computational prediction of chemical reactions is a key part of an efficient drug discovery process. In this review, we discuss important parts of this field, with a focus on utilizing reaction data to build predictive models, the existing programs for synthesis prediction, and usage of quantum mechanics and molecular mechanics (QM/MM) to explore chemical reactions. We also outline potential future developments with an emphasis on pre-competitive collaboration opportunities.

Automating drug discovery

Small-molecule drug discovery can be viewed as a challenging multidimensional problem in which various characteristics of compounds - including efficacy, pharmacokinetics and safety - need to be optimized in parallel to provide drug candidates. Recent advances in areas such as microfluidics-assisted chemical synthesis and biological testing, as well as artificial intelligence systems that improve a design hypothesis through feedback analysis, are now providing a basis for the introduction of greater automation into aspects of this process. This could potentially accelerate time frames for compound discovery and optimization and enable more effective searches of chemical space. However, such approaches also raise considerable conceptual, technical and organizational challenges, as well as scepticism about the current hype around them. This article aims to identify the approaches and technologies that could be implemented robustly by medicinal chemists in the near future and to critically analyse the opportunities and challenges for their more widespread application.

Best Practices of Computer-Aided Drug Discovery: Lessons Learned from the Development of a Preclinical Candidate for Prostate Cancer with a New Mechanism of Action

Small-molecule drug design is a complex and iterative decision-making process relying on pre-existing knowledge and driven by experimental data. Low-molecular-weight chemicals represent an attractive therapeutic option, as they are readily accessible to organic synthesis and can easily be characterized.1 Their potency as well as pharmacokinetic and pharmacodynamic properties can be systematically and rationally investigated and ultimately optimized via expert science behind medicinal chemistry and methods of computer-aided drug design (CADD). In recent years, significant advances in molecular modeling techniques have afforded a variety of tools to effectively identify potential binding pockets on prospective targets, to map key interactions between ligands and their binding sites, to construct and assess energetics of the resulting complexes, to predict ADMET properties of candidate compounds, and to systematically analyze experimental and computational data to derive meaningful structure-activity relationships leading to the creation of a drug candidate. This Perspective describes a real case of a drug discovery campaign accomplished in a relatively short time with limited resources. The study integrated an arsenal of available molecular modeling techniques with an array of experimental tools to successfully develop a novel class of potent and selective androgen receptor inhibitors with a novel mode of action. It resulted in the largest academic licensing deal in Canadian history, totaling $142M. This project exemplifies the importance of team science, an integrative approach to drug discovery, and the use of best practices in CADD. We posit that the lessons learned and best practices for executing an effective CADD project can be applied, with similar success, to many drug discovery projects in both academia and industry.